基于3D卷积神经网络的肝脏自动分割方法

原发性肝脏恶性肿瘤是我国高发且危害极大的恶性肿瘤。肝脏手术（如肿瘤切除、活体肝移植等）是各种常见肝脏良恶性疾病的主要治疗方法之一。从医学影像中将肝脏组织准确地分割出来,是计算机辅助肝脏疾病诊断与手术规划中一个基础且至关重要的步骤。针对肝脏分割的特异性及分割难点,提出3D卷积神经网络（3DCNN）肝脏自动分割算法模型。3DCNN基于对体数据的训练能很好地学习到肝脏图像平面与空间信息。通过将深度监督机制无缝地整合到3DCNN中,能够有效解决梯度消失或爆炸的优化问题,加快收敛速度的同时提高分辨能力。最后,将初始分割结果作为先验信息,采用基于多星凸约束的图割算法做进一步的分割优化。实验结果表明该分割模型能够将肝脏组织从腹部CT图像中精确分割。     

A dual-stage method for lesion segmentation on digital mammograms

Mass lesion segmentation on mammograms is a challenging task since mass lesions are usually embedded and hidden in varying densities of parenchymal tissue structures. In this article, we present a method for automatic delineation of lesion boundaries on digital mammograms. This method utilizes a geometric active contour model that minimizes an energy function based on the homogeneities inside and outside of the evolving contour. Prior to the application of the active contour model, a radial gradient index (RGI)-based segmentation method is applied to yield an initial contour closer to the lesion boundary location in a computationally efficient manner. Based on the initial segmentation, an automatic background estimation method is applied to identify the effective circumstance of the lesion, and a dynamic stopping criterion is implemented to terminate the contour evolution when it reaches the lesion boundary. By using a full-field digital mammography database with 739 images, we quantitatively compare the proposed algorithm with a conventional region-growing method and an RGI-based algorithm by use of the area overlap ratio between computer segmentation and manual segmentation by an expert radiologist. At an overlap threshold of 0.4, 85% of the images are correctly segmented with the proposed method, while only 69% and 73% of the images are correctly delineated by our previous developed region-growing and RGI methods, respectively. This resulting improvement in segmentation is statistically significant.     

Extracting Lungs from CT Images via Deep Convolutional Neural Network Based Segmentation and Two-Pass Contour Refinement

Lung segmentation is a key step of thoracic computed tomography (CT) image processing, and it plays an important role in computer-aided pulmonary disease diagnostics. However, the presence of image noises, pathologies, vessels, individual anatomical varieties, and so on makes lung segmentation a complex task. In this paper, we present a fully automatic algorithm for segmenting lungs from thoracic CT images accurately. An input image is first spilt into a set of non-overlapping fixed-sized image patches, and a deep convolutional neural network model is constructed to extract initial lung regions by classifying image patches. Superpixel segmentation is then performed on the preprocessed thoracic CT image, and the lung contours are locally refined according to corresponding superpixel contours with our adjacent point statistics method. Segmented lung contours are further globally refined by an edge direction tracing technique for the inclusion of juxta-pleural lesions. Our algorithm is tested on a group of thoracic CT scans with interstitial lung diseases. Experiments show that our algorithm creates an average Dice similarity coefficient of 97.95% and Jaccard’s similarity index of 94.48%, with 2.8% average over-segmentation rate and 3.3% under-segmentation rate compared with manually segmented results. Meanwhile, it shows better performance compared with several feature-based machine learning methods and current methods on lung segmentation.     

基于数学形态学的CT图像肝脏肿瘤提取研究

目的 肝脏肿瘤的提取是肝脏三维可视化、手术规划和模拟的基础,而当前肿瘤分割存在干预过多和分割效果不佳的问题.方法 本文通过对腹部CT图像进行高斯平滑以去除图像噪声和细密纹理,计算出图像的形态学梯度并用高、低帽变换进行增强,再根据用户选择点计算内部和外部标记符,然后基于控制标记符的分水岭算法分割图像,提取出腹部CT图像中的病变组织.结果 实验结果表明,该算法能够在较少的人工干预下快速分割出肝脏病变组织.结论 该算法实现了腹部CT图像中肝脏病变组织的提取.     

Level Set Segmentation of Breast Masses in Contrast-Enhanced Dedicated Breast CT and Evaluation of Stopping Criteria

Dedicated breast CT (bCT) produces high-resolution 3D tomographic images of the breast, fully resolving fibroglandular tissue structures within the breast and allowing for breast lesion detection and assessment in 3D. In order to enable quantitative analysis, such as volumetrics, automated lesion segmentation on bCT is highly desirable. In addition, accurate output from CAD (computer-aided detection/diagnosis) methods depends on sufficient segmentation of lesions. Thus, in this study, we present a 3D lesion segmentation method for breast masses in contrast-enhanced bCT images. The segmentation algorithm follows a two-step approach. First, 3D radial-gradient index segmentation is used to obtain a crude initial contour, which is then refined by a 3D level set-based active contour algorithm. The data set included contrast-enhanced bCT images from 33 patients containing 38 masses (25 malignant, 13 benign). The mass centers served as input to the algorithm. In this study, three criteria for stopping the contour evolution were compared, based on (1) the change of region volume, (2) the average intensity in the segmented region increase at each iteration, and (3) the rate of change of the average intensity inside and outside the segmented region. Lesion segmentation was evaluated by computing the overlap ratio between computer segmentations and manually drawn lesion outlines. For each lesion, the overlap ratio was averaged across coronal, sagittal, and axial planes. The average overlap ratios for the three stopping criteria ranged from 0.66 to 0.68 (dice coefficient of 0.80 to 0.81), indicating that the proposed segmentation procedure is promising for use in quantitative dedicated bCT analyses.     

基于新型深度全卷积网络的肝脏CT影像三维区域自动分割

肝脏分割对于肝肿瘤肝段切除及肝移植体积测量具有重要的临床价值。由于在CT影像中肝脏与邻近脏器的灰度值相似性很高,因此对肝脏区域的三维自动分割是一项具有挑战性的难题。为解决精准肝脏分割的问题,提出一种新型的深度全卷积网络结构3DUnet-C2。该结构充分利用肝脏CT图像的三维空间信息,并有效结合肝脏区域的浅层特征和深层特征。特别地,还提出一种新的3DUnet-C2网络训练策略,通过选取清晰图像,并从图像中截取肝脏区域作为样本进行训练的方式,得到初步3DUnet-C2模型权重,并使用该权重来初始化3DUnet-C2的网络参数,从而使网络达到收敛。最后,针对3DUnet-C2网络分割肝脏边界不精准的问题,在原有3DUnet-C2网络模型的基础上,运用三维条件随机场构建3DUnet-C2-CRF模型来优化肝脏分割边界。为了验证所提出三维分割模型的性能,从ISBI2017 Liver Tumor Segmentation Challenge的数据集中选取100张CT图像用于训练、验证和测试,3DUnet-C2-CRF模型在随机选取的20张测试集上的分割准确率的Dice系数为96.9%,高于3DUnet和Vnet模型的Dice系数。实验结果表明,3DUnet-C2-CRF模型具有更好的特征表达能力以及更强的泛化性能,从而可提升模型的分割准确率。     

一种基于Snake模型的脑部CT图像分割新算法

针对目前传统的Snake模型图像分割算法的力场捕捉范围小、对初始轮廓的选取敏感以及对轮廓曲线难以收敛到 细小深凹边界的缺陷,提出一种基于Snake 模型的脑部CT图像分割新算法。算法首先运用Canny 边缘算子对图像进行 边缘检测,将边缘检测图像叠加到原始图像上,然后再运用Snake模型和梯度向量流（GVF）Snake模型分别对叠加图像进 行分割。实验结果表明,该算法克服了传统Snake 模型和GVF Snake 模型因边缘轮廓不清晰造成的漏分割情况,防止了 GVF Snake模型由于GVF力场的相互作用所造成的过分割现象,同时,还能促使轮廓线收敛到细小深凹边界,提高定位精 度,具有更好的分割效果。     

U-Net改进及其在新冠肺炎图像分割的应用

CT成像已成为检测新型冠状病毒肺炎（COVID-19）最重要的步骤之一。针对手动分割患者胸部CT图像中毛玻璃混浊区域繁琐的问题提出了一种自注意力循环残差U型网络模型来实现COVID-19患者肺部CT图像的自动分割,辅助医生诊断。在U-Net模型的基础上引入了循环残差模块和自注意力机制来加强对特征信息的抓取从而提升分割精度。在公开数据集上的分割实验结果显示,该算法的Dice系数、敏感度和特异度分别达到了85.36%、76.64%和76.25%,与其他算法相比具有良好的分割效果。     

基于多尺度编码-解码网络的皮肤病变图像分割

针对皮肤病变图像分割在医疗诊断中的作用,提出一种基于多尺度编码-解码网络的皮肤病变图像分割算法。该算法继承了SegNet网络结构的训练速度快、训练模型存储小等特点,采用多尺度输入的方式增强了网络对皮肤病变图像的充分学习。此外,在编码网络中的pool2层输出一个二进制双线性插值的中间预测特征图到解码层的最后一层卷积块进行级联输入提高最终的分割精度。实验结果表明,采用多尺度编码-解码网络对皮肤病变图像分割具有极好的效果,在其他医学图像分割方面也能进行广泛应用。     

基于级联式三维卷积神经网络的肝肿瘤自动分割

目的:根据肝肿瘤CT影像中的特异性、分割难点以及残差网络思想,提出一种基于级联式卷积神经网络的全自动CT图像肝脏肿瘤分割方法。方法:首先根据临床知识对CT数据进行预处理,减少干扰;然后基于一个肝脏粗分割网络对肝脏进行分割,并根据分割结果坐标选取肝脏作为感兴趣区域;最后在感兴趣区域内对肿瘤进行精准分割。结果:通过级联式网络分割可以有效减少计算时间以及避免其它组织的干扰,从而实现肝肿瘤的快速分割。本研究提出的方法在2017年MICCAI肝肿瘤分割公开比赛数据集LiTS中进行测试,平均Dice分数为0.663,证实了其对肝肿瘤分割的有效性。结论:基于级联式卷积神经网络的全自动CT图像肝脏肿瘤分割方法可以实现肿瘤的快速分割。后期研究将继续增加数据量,对肿瘤进行分类,从而进一步完善模型。     

基于图谱的肝脏CT三维自动分割研究

目的在肝脏外科手术或肝脏病理研究中,计算肝脏体积是重要步骤。由于肝脏外形复杂、临近组织灰度值与之接近等特点,肝脏的自动医学图像分割仍是医学图像处理中的难点之一。方法本文采用图谱结合3D非刚性配准的方法,同时加入肝脏区域搜索算法,实现了鲁棒性较高的肝脏自动分割程序。首先,利用20套训练图像创建图谱,然后程序自动搜索肝脏区域,最后将图谱与待分割CT图像依次进行仿射配准和B样条配准。配准以后的图谱肝脏轮廓即可表示为目标肝脏分割轮廓,进而计算出肝脏体积。结果评估结果显示,上述方法在肝脏体积误差方面表现出色,达到77分,但在局部（主要在肝脏尖端）出现较大的误差。结论该方法分割临床肝脏CT图像具有可行性。     

一种基于概率配分和最大模糊熵的CT图像分割方法

为了从CT图像中提取到多个组织的解剖特征,克服运算速度快与运算结果不稳定的矛盾,提出了一种基于概率分布和模糊熵的CT图像分割方法。为了找到分割灰度图象的最佳阈值,根据模糊聚类和概率配分之间的关系,以及模糊熵有最大值的必要条件,从而得到各类的概率配分,因此在搜索阈值组合时,先搜索满足各类概率配分的阈值,然后从这些阈值中搜索使模糊熵最大的阈值。实验结果表明该方法能很好地完成CT图象的分割。此算法运算速度较快;与用遗传算法、模拟退火算法相比较,运算结果稳定,分割更准确。     

基于改进区域生长算法的肝脏分割方法研究

目的：把肝脏从医学图像中提取出来,为肝脏三维定位以及放疗计划制定提供准确的数据。肝脏与其周围器官组织灰度差别小、边界不明显,而传统区域生长算法生长准则单一,不能满足分割精确度需求,并且未经处理的轮廓比较粗糙。针对这些问题,本文提出一种改进的区域生长算法。方法：本文算法主要从三个方面改进：基于先验经验和肝脏特性的种子区域选择;基于Canny算子边缘检测结果的区域生长准则动态优化;基于漫水填充法和曲线拟合的轮廓后处理。结果：本文使用多套临床实际腹部CT序列测试算法,以医生手动勾画结果为标准进行评价。在大多数CT切片上的肝脏自动分割都能取得较好的结果,并且分割用时很短,保证了效率。结论：测试结果表明,本文算法在动态控制区域生长和平滑轮廓方面有很好的作用,在保证速度的同时有效提高了肝脏自动分割精度。     

Fast segmentation of bone in CT images using 3D adaptive thresholding

Fast bone segmentation is often important in computer-aided medical systems. Thresholding-based techniques have been widely used to identify the object of interest (bone) against dark backgrounds. However, the darker areas that are often present in bone tissue may adversely affect the results obtained using existing thresholding-based segmentation methods. We propose an automatic, fast, robust and accurate method for the segmentation of bone using 3D adaptive thresholding. An initial segmentation is first performed to partition the image into bone and non-bone classes, followed by an iterative process of 3D correlation to update voxel classification. This iterative process significantly improves the thresholding performance. A post-processing step of 3D region growing is used to extract the required bone region. The proposed algorithm can achieve sub-voxel accuracy very rapidly. In our experiments, the segmentation of a CT image set required on average less than 10 s per slice. This execution time can be further reduced by optimizing the iterative convergence process.     

基于边缘监督的肝部超声图像包膜分割网络

肝纤维化、肝硬化的早期发现对临床治疗和预后评估具有重要意义。而肝包膜的形态和纹理特征是计算机辅助肝硬化诊断的重要依据。本文提出一种基于边缘监督的肝部超声图像包膜分割网络。该网络以常用的分割模型UNet为基础，引入空洞卷积，扩大感受野；同时，添加了边缘监督模块，从而将特征学习主要聚焦在图像梯度较大的部分；此外，还设计了混合加权损失函数，来缓解肝包膜部分与其他区域之间的极度不平衡情况。实验结果表明，本文提出的ES-UNet网络结构平均Dice系数相比原始UNet提高了0.171 5，平均交并比（MIoU）提高了0.021 5，其他指标也有较明显的提高，可见，本文算法的各个组件对模型分割性能的优化都有一定的贡献，改进后的模型可以实现肝包膜的精确分割。     

Liver segmentation for CT images using GVF snake

Accurate liver segmentation on computed tomography (CT) images is a challenging task especially at sites where surrounding tissues (e.g., stomach, kidney) have densities similar to that of the liver and lesions reside at the liver edges. We have developed a method for semiautomatic delineation of the liver contours on contrast-enhanced CT images. The method utilizes a snake algorithm with a gradient vector flow (GVF) field as its external force. To improve the performance of the GVF snake in the segmentation of the liver contour, an edge map was obtained with a Canny edge detector, followed by modifications using a liver template and a concavity removal algorithm. With the modified edge map, for which unwanted edges inside the liver were eliminated, the GVF field was computed and an initial liver contour was formed. The snake algorithm was then applied to obtain the actual liver contour. This algorithm was extended to segment the liver volume in a slice-by-slice fashion, where the result of the preceding slice constrained the segmentation of the adjacent slice. 551 two-dimensional liver images from 20 volumetric images with colorectal metastases spreading throughout the livers were delineated using this method, and also manually by a radiologist for evaluation. The difference ratio, which is defined as the percentage ratio of mismatching volume between the computer and the radiologist's results, ranged from 2.9% to 7.6% with a median value of 5.3%.     

Automatic registration between 3D intra-operative ultrasound and pre-operative CT images of the liver based on robust edge matching

The registration of a three-dimensional (3D) ultrasound (US) image with a computed tomography (CT) or magnetic resonance image is beneficial in various clinical applications such as diagnosis and image-guided intervention of the liver. However, conventional methods usually require a time-consuming and inconvenient manual process for pre-alignment, and the success of this process strongly depends on the proper selection of initial transformation parameters. In this paper, we present an automatic feature-based affine registration procedure of 3D intra-operative US and pre-operative CT images of the liver. In the registration procedure, we first segment vessel lumens and the liver surface from a 3D B-mode US image. We then automatically estimate an initial registration transformation by using the proposed edge matching algorithm. The algorithm finds the most likely correspondences between the vessel centerlines of both images in a non-iterative manner based on a modified Viterbi algorithm. Finally, the registration is iteratively refined on the basis of the global affine transformation by jointly using the vessel and liver surface information. The proposed registration algorithm is validated on synthesized datasets and 20 clinical datasets, through both qualitative and quantitative evaluations. Experimental results show that automatic registration can be successfully achieved between 3D B-mode US and CT images even with a large initial misalignment.     

MAUNet:用于皮肤病变分割的轻量级模型

针对当前深度学习分割算法参数数量多和计算复杂度高的问题,提出了一种融合多种注意力机制的轻量级模型MAUNet用于皮肤病变分割。该模型在UNet网络基础上融合深度可分离卷积和门控注意力机制模块,用于提取全局和局部特征信息;融入外部注意力机制模块来增强样本间的联系;利用空间和通道注意力模块分别提取通道和空间特征。以ISIC2017皮肤病公开数据集作为数据源,改进的UNet模型实现特征提取与分类。与基线模型UNet相比,平均交并比和Dice相似性系数分别提高了2.18%和1.28%,同时参数量和计算复杂度仅为基线模型的2.1%和0.58%。实验结果表明该模型在参数数量平衡性、计算复杂度和分割检测性能上均达到了较好的水平。     

基于卷积神经网络和图像显著性的心脏CT图像分割

目的心脏医学影像中,感兴趣部分的提取与分割是诊断心脏病变部位的关键。由于心脏舒张、收缩以及血液的流动,心脏CT图像易出现弱边界、伪影,传统分割算法易产生过度分割的情况。为此,提出一种基于卷积神经网络和图像显著性的心脏CT图像分割方法。方法采用卷积神经网络对目标区域进行定位,滤除肋骨、肌肉等造影对比不明显部分,截取出感兴趣区域,结合感兴趣区域的对比度计算并提高感兴趣区域的心脏组织的显著值。通过获得的显著值图像截取心脏图像,并与区域生长算法的分割结果进行对比。最后使用泰州人民医院11例患者的影像数据对算法模型进行训练和测试,随机选择9例用于训练,剩余2例用于测试。结果所提算法模型在心底、心中、心尖3个心脏分段的分割正确率分别达到了92.79%、92.79%、94.11%,均优于基于区域生长的分割方法。结论基于卷积神经网络和图像显著性的分割方法能够准确获取心脏的外围轮廓,轮廓边缘更加平滑,完全能够满足CT图像序列的心脏全自动分割任务需求,分割后的图像更有利于医生对患者心脏健康状况和病变部位的观察。     

Les complications pariétales du kyste hydatique du foie. à propos de deux cas en Tunisie

The aim of this study is to consider the parietal complications of the hydatid cyst of the liver: the subcutaneous rupture of the cyst and spontaneous cutaneous fistula of liver hydatid cyst. 1^st case: A 24-year-old woman, who underwent surgery 10 years ago for hydatid cyst of the liver, was admitted for a right hypochondrium mass and a fistula draining clear liquid containing cystic elements. Computed tomography (CT) showed a large cystic lesion in the subcutaneous tissue communicating with another cystic mass in the liver. The diagnosis of a cyst-cutaneous fistula due to a peritoneal hydatid cyst was established. The patient underwent surgical treatment and recovered uneventfully. 2^nd case: A 40-year-old woman presented with a mass in her right hypochondrium. The diagnosis of subcutaneous rupture of a hydatid cyst of liver was established by ultrasonography and CT-scan. The patient underwent surgical treatment and recovered uneventfully. Parietal complications of hydatid cyst of the liver are extremely rare, clinical presentation can be derailing. The diagnosis is usually established by ultrasonography and CT-scan.